Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating indirect objects or relative clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "that" and its variations, indicating a focus on clauses or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    which is qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =")
    -0.52
    +-+-
    -0.51
    volles
    -0.51
    cive
    -0.50
    ered
    -0.50
    ]='\
    -0.50
    其中的
    -0.49
    fören
    -0.48
     ful
    -0.47
    iname
    -0.47
    POSITIVE LOGITS
     admittedly
    1.01
     obviously
    0.94
     unfortunately
    0.92
    obviously
    0.90
     thankfully
    0.89
     malheureusement
    0.88
     nobody
    0.86
     apparently
    0.86
     fortunately
    0.85
     obviamente
    0.85
    Act Density 0.118%

    No Known Activations